kernfs: implement i_generation

Set i_generation for kernfs inode. This is required to implement
exportfs operations. The generation is 32-bit, so it's possible the
generation wraps up and we find stale files. To reduce the posssibility,
we don't reuse inode numer immediately. When the inode number allocation
wraps, we increase generation number. In this way generation/inode
number consist of a 64-bit number which is unlikely duplicated. This
does make the idr tree more sparse and waste some memory. Since idr
manages 32-bit keys, idr uses a 6-level radix tree, each level covers 6
bits of the key. In a 100k inode kernfs, the worst case will have around
300k radix tree node. Each node is 576bytes, so the tree will use about
~150M memory. Sounds not too bad, if this really is a problem, we should
find better data structure.

Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 10 insertions, 1 deletions

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 8ad7a17895fe..33f711f6b86e 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -623,6 +623,8 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
                                              unsigned flags)
 {
         struct kernfs_node *kn;
+        u32 gen;
+        int cursor;
         int ret;
 
         name = kstrdup_const(name, GFP_KERNEL);
@@ -635,12 +637,17 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 
         idr_preload(GFP_KERNEL);
         spin_lock(&kernfs_idr_lock);
-        ret = idr_alloc(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
+        cursor = idr_get_cursor(&root->ino_idr);
+        ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
+        if (ret >= 0 && ret < cursor)
+                root->next_generation++;
+        gen = root->next_generation;
         spin_unlock(&kernfs_idr_lock);
         idr_preload_end();
         if (ret < 0)
                 goto err_out2;
         kn->ino = ret;
+        kn->generation = gen;
 
         atomic_set(&kn->count, 1);
         atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
@@ -884,6 +891,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 
         idr_init(&root->ino_idr);
         INIT_LIST_HEAD(&root->supers);
+        root->next_generation = 1;
 
         kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO,
                                KERNFS_DIR);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index fb4b4a79a0d6..79cdae4758fb 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -220,6 +220,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
         inode->i_private = kn;
         inode->i_mapping->a_ops = &kernfs_aops;
         inode->i_op = &kernfs_iops;
+        inode->i_generation = kn->generation;
 
         set_default_inode_attr(inode, kn->mode);
         kernfs_refresh_inode(kn, inode);